dragon-ml-toolbox 20.1.0__tar.gz → 20.2.0__tar.gz

{dragon_ml_toolbox-20.1.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-20.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.1.0
+Version: 20.2.0
 Summary: Complete pipelines and helper tools for data science and machine learning projects.
 Author-email: Karl Luigi Loza Vidaurre <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-20.1.0 → dragon_ml_toolbox-20.2.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.1.0
+Version: 20.2.0
 Summary: Complete pipelines and helper tools for data science and machine learning projects.
 Author-email: Karl Luigi Loza Vidaurre <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-20.1.0 → dragon_ml_toolbox-20.2.0}/ml_tools/ML_configuration/_training.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 from .._core import get_logger
 from ..path_manager import make_fullpath
+from ..keys._keys import MLTaskKeys
 
 from ._base_model_config import _BaseModelParams
 
@@ -30,6 +31,9 @@ class DragonTrainingConfig(_BaseModelParams):
                  test_size: float,
                  initial_learning_rate: float,
                  batch_size: int,
+                 task: str,
+                 device: str,
+                 finalized_filename: str,
                  random_state: int = 101,
                  **kwargs: Any) -> None:
         """  
@@ -38,6 +42,9 @@ class DragonTrainingConfig(_BaseModelParams):
             test_size (float): Proportion of data for test set.
             initial_learning_rate (float): Starting learning rate.
             batch_size (int): Number of samples per training batch.
+            task (str): Type of ML task (use TaskKeys).
+            device (str): Device to run training on.
+            finalized_filename (str): Filename for the Dragon ML Finalized-file.
             random_state (int): Seed for reproducibility.
             **kwargs: Additional training parameters as key-value pairs.
         """
@@ -45,7 +52,15 @@ class DragonTrainingConfig(_BaseModelParams):
         self.test_size = test_size
         self.initial_learning_rate = initial_learning_rate
         self.batch_size = batch_size
-        self.random_state = random_state
+        self.device = device
+        self.finalized_filename = finalized_filename
+        self.random_state = random_state        
+        
+        # validate task
+        if task not in MLTaskKeys.ALL_TASKS:
+            _LOGGER.error(f"Invalid task '{task}'. Must be one of: {MLTaskKeys.ALL_TASKS}")
+            raise ValueError()
+        self.task = task
         
         # Process kwargs with validation
         for key, value in kwargs.items():

{dragon_ml_toolbox-20.1.0 → dragon_ml_toolbox-20.2.0}/ml_tools/ML_datasetmaster/_base_datasetmaster.py

@@ -172,6 +172,12 @@ class _BaseDatasetMaker(ABC):
         y_train_arr = y_train.to_numpy() if isinstance(y_train, (pandas.Series, pandas.DataFrame)) else y_train
         y_val_arr = y_val.to_numpy() if isinstance(y_val, (pandas.Series, pandas.DataFrame)) else y_val
         y_test_arr = y_test.to_numpy() if isinstance(y_test, (pandas.Series, pandas.DataFrame)) else y_test
+        
+        # --- Ensure targets are 2D (N, 1) if they are currently 1D (N,) ---
+        if y_train_arr.ndim == 1: y_train_arr = y_train_arr.reshape(-1, 1)
+        if y_val_arr.ndim == 1:   y_val_arr = y_val_arr.reshape(-1, 1)
+        if y_test_arr.ndim == 1:  y_test_arr = y_test_arr.reshape(-1, 1)
+        # ------------------------------------------------------------------
 
         if self.target_scaler is None:
             _LOGGER.info("Fitting a new DragonScaler on training targets.")

{dragon_ml_toolbox-20.1.0 → dragon_ml_toolbox-20.2.0}/ml_tools/ML_scaler/_ML_scaler.py

@@ -127,9 +127,14 @@ class DragonScaler:
         if self.mean_ is None or self.std_ is None or self.continuous_feature_indices is None:
             # If not fitted, return as is
             return data
-
+        
         data_clone = data.clone()
         
+        # Robust check: If data is 1D, assume it's a single feature/target column and reshape it to (N, 1) for the operation, then reshape back.
+        input_is_1d = (data_clone.ndim == 1)
+        if input_is_1d:
+            data_clone = data_clone.view(-1, 1)
+
         # Ensure mean and std are on the same device as the data
         mean = self.mean_.to(data.device)
         std = self.std_.to(data.device)
@@ -143,6 +148,9 @@ class DragonScaler:
         # Place the scaled features back into the cloned tensor
         data_clone[:, self.continuous_feature_indices] = scaled_features
         
+        if input_is_1d:
+            return data_clone.view(-1)
+        
         return data_clone
 
     def inverse_transform(self, data: torch.Tensor) -> torch.Tensor:
@@ -151,9 +159,13 @@ class DragonScaler:
         """
         if self.mean_ is None or self.std_ is None or self.continuous_feature_indices is None:
             return data
-            
+        
         data_clone = data.clone()
         
+        input_is_1d = (data_clone.ndim == 1)
+        if input_is_1d:
+            data_clone = data_clone.view(-1, 1)
+        
         mean = self.mean_.to(data.device)
         std = self.std_.to(data.device)
         
@@ -164,6 +176,9 @@ class DragonScaler:
         
         data_clone[:, self.continuous_feature_indices] = original_scale_features
         
+        if input_is_1d:
+            return data_clone.view(-1)
+        
         return data_clone
 
     def _get_state(self):

{dragon_ml_toolbox-20.1.0 → dragon_ml_toolbox-20.2.0}/ml_tools/keys/_keys.py

@@ -198,6 +198,13 @@ class MLTaskKeys:
     SEQUENCE_VALUE = "sequence-to-value"
     
     ALL_BINARY_TASKS = [BINARY_CLASSIFICATION, MULTILABEL_BINARY_CLASSIFICATION, BINARY_IMAGE_CLASSIFICATION, BINARY_SEGMENTATION]
+    
+    ALL_TASKS = [REGRESSION, MULTITARGET_REGRESSION, 
+                 BINARY_CLASSIFICATION, MULTICLASS_CLASSIFICATION, MULTILABEL_BINARY_CLASSIFICATION, 
+                 BINARY_IMAGE_CLASSIFICATION, MULTICLASS_IMAGE_CLASSIFICATION, 
+                 BINARY_SEGMENTATION, MULTICLASS_SEGMENTATION, 
+                 OBJECT_DETECTION, 
+                 SEQUENCE_SEQUENCE, SEQUENCE_VALUE]
 
 
 class _PublicTaskKeys:

{dragon_ml_toolbox-20.1.0 → dragon_ml_toolbox-20.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "20.1.0"
+version = "20.2.0"
 description = "Complete pipelines and helper tools for data science and machine learning projects."
 authors = [
     { name = "Karl Luigi Loza Vidaurre", email = "luigiloza@gmail.com" }